It is uncontroversial that language resources are of paramount importance to the processes of conceiving and developing computer products. Indeed, linguistic resources play an important role not only as directly deployed linguistic data but also in the production of novel resources and the development of new tools.
Less computerised natural languages are, nonetheless, fraught with notable scarcity in terms of linguistic resources; such resources are of prime importance and utility to the integration of these languages in the new technology of information. From the foregoing, it emerges that one of the major concerns in Natural Language Processing (NLP) is the availability of such resources. Nowadays, embarking on NLP fieldwork essentially necessitates a basic preparation (encoding of graphic systems, keyboard layouts, etc.) of the language in question before undertaking any further work of matching to the international norms and specifications. This preparation is sorely needed to maximally achieve the re-usability of resources and developed tools to a maximum and guarantee inter-operability with other languages.

In fact, in the case of Amazigh, the process of standardisation coupled with the generalisation of Tifinaghe characters use at the level of information technologies have both paved the way to the creation of NLP tools and facilitated the management of linguistic resources (LRs), both monolingual and multilingual. There remains, nonetheless, a lot of effort to be invested to ease the use of Amazigh and contribute to its promotion.

While bringing together the efforts of a whole range of national and international researchers who work in NLP, this workshop is meant to strengthen the culture of mutual exchange of experience on language resources and to encourage research projects on natural language processing. This call is headed to researchers from different national and international institutions.

Topics

Researchers’ contributions are welcome on one or more of the following points:
• Language resources from design to use within a bilingual/multilingual context;
• Application of annotated, standardised and/or shared resources’ (both vocal and textual) norms;
• Basic solutions for resources computerisation (encoding, typing, normalisation, etc.,);
• NLP Language resources management systems;
• Technical methodologies for building corpora and other linguistic resources (lexical, grammatical, etc.)
• Reflections on language resources needs for less resourced languages;
• LR-exploiting NLP tools, such as:
- analysis and annotation tools along different linguistic levels (morphology, syntax, semantics, etc.);
- tools yielding access to language resources;
- indexation and information retrieval;
- knowledge discovery;
- multilingual corpora alignment;
- natural language generation;
- operating systems’ localisation.